|
gptkbp:instance_of
|
gptkb:Data
|
|
gptkbp:application
|
object detection
transfer learning
image retrieval
semantic segmentation
image captioning
instance segmentation
style transfer
visual question answering
|
|
gptkbp:categories
|
80
|
|
gptkbp:collection
|
crowdsourcing
|
|
gptkbp:contains
|
annotations
images
captions
bounding boxes
segmentation masks
|
|
gptkbp:creator
|
gptkb:Microsoft
|
|
gptkbp:data_type
|
structured
visual
large-scale
textual
|
|
gptkbp:evaluates
|
Intersection over Union (Io U)
mean Average Precision (m AP)
|
|
gptkbp:has_artwork
|
330,000
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
MS COCO dataset
|
|
gptkbp:image
|
gptkb:Flickr
gptkb:MS_Research
|
|
gptkbp:is_divided_into
|
gptkb:test_subjects
gptkb:train
val
|
|
gptkbp:is_documented_in
|
gptkb:JSON
|
|
gptkbp:is_popular_in
|
computer vision community
|
|
gptkbp:license
|
gptkb:Creative_Commons_Attribution_4.0_License
|
|
gptkbp:primary_use
|
object detection
image segmentation
captioning
|
|
gptkbp:provides_information_on
|
gptkb:2014
gptkb:2015
gptkb:2016
gptkb:2017
gptkb:2018
gptkb:2019
gptkb:2020
gptkb:2021
gptkb:2022
gptkb:2023
|
|
gptkbp:release_year
|
gptkb:2014
|
|
gptkbp:resolution
|
varied
|
|
gptkbp:supports
|
gptkb:machine_learning
image processing
deep learning
|
|
gptkbp:website
|
cocodataset.org
|
|
gptkbp:bfsParent
|
gptkb:Deep_Lab_v3
|
|
gptkbp:bfsLayer
|
6
|